no code implementations • 2 May 2024 • Zhenya Yang, Kai Chen, Yonghao Long, Qi Dou
The results demonstrate great potential of our proposed method to enhance the efficiency and variety of simulations available for surgical education and robot learning.
no code implementations • 1 May 2024 • Liu Yang, Shuowei Cai, Di Chai, Junxue Zhang, Han Tian, Yilun Jin, Kun Guo, Kai Chen, Qiang Yang
To this core, we propose PackVFL, an efficient VFL framework based on packed HE (PackedHE), to accelerate the existing HE-based VFL algorithms.
no code implementations • 1 May 2024 • Zhili Liu, Yunhao Gou, Kai Chen, Lanqing Hong, Jiahui Gao, Fei Mi, Yu Zhang, Zhenguo Li, Xin Jiang, Qun Liu, James T. Kwok
As the capabilities of large language models (LLMs) have expanded dramatically, aligning these models with human values presents a significant challenge, posing potential risks during deployment.
no code implementations • 23 Apr 2024 • Qian Xu, Kai Chen, Xueqi Shen, Lei Xing, Yi Huang, Tian Hong Loh
By counting the number of pass/fail occurrences of a DUT (Device under Test) in the stirring process in a reverberation chamber (RC), the threshold electric field (E-field) level can be well estimated without tuning the input power and repeating the whole testing many times.
no code implementations • 22 Apr 2024 • Yaofeng Xie, Lingwei Kong, Kai Chen, Ziqiang Zheng, Xiao Yu, Zhibin Yu, Bing Zheng
Learning-based underwater image enhancement (UIE) methods have made great progress.
no code implementations • 16 Apr 2024 • Yanze Li, Wenhua Zhang, Kai Chen, Yanxin Liu, Pengxiang Li, Ruiyuan Gao, Lanqing Hong, Meng Tian, Xinhai Zhao, Zhenguo Li, Dit-yan Yeung, Huchuan Lu, Xu Jia
Large Vision-Language Models (LVLMs), due to the remarkable visual reasoning ability to understand images and videos, have received widespread attention in the autonomous driving domain, which significantly advances the development of interpretable end-to-end autonomous driving.
no code implementations • 10 Apr 2024 • Jiahao Wang, Wenqi Shao, Mengzhao Chen, Chengyue Wu, Yong liu, Kaipeng Zhang, Songyang Zhang, Kai Chen, Ping Luo
We first "LLaMAfy" a standard ViT step-by-step to align with LLaMA's architecture, and find that directly applying a casual mask to the self-attention brings an attention collapse issue, resulting in the failure to the network training.
1 code implementation • 9 Apr 2024 • Chonghua Wang, Haodong Duan, Songyang Zhang, Dahua Lin, Kai Chen
Recently, the large language model (LLM) community has shown increasing interest in enhancing LLMs' capability to handle extremely long documents.
2 code implementations • 9 Apr 2024 • Xiaoyi Dong, Pan Zhang, Yuhang Zang, Yuhang Cao, Bin Wang, Linke Ouyang, Songyang Zhang, Haodong Duan, Wenwei Zhang, Yining Li, Hang Yan, Yang Gao, Zhe Chen, Xinyue Zhang, Wei Li, Jingwen Li, Wenhai Wang, Kai Chen, Conghui He, Xingcheng Zhang, Jifeng Dai, Yu Qiao, Dahua Lin, Jiaqi Wang
The Large Vision-Language Model (LVLM) field has seen significant advancements, yet its progression has been hindered by challenges in comprehending fine-grained visual content due to limited resolution.
Ranked #12 on Visual Question Answering on MM-Vet
no code implementations • 1 Apr 2024 • Rongjie Li, Songyang Zhang, Dahua Lin, Kai Chen, Xuming He
Scene graph generation (SGG) aims to parse a visual scene into an intermediate graph representation for downstream reasoning tasks.
1 code implementation • 26 Mar 2024 • Zheng Cai, Maosong Cao, Haojiong Chen, Kai Chen, Keyu Chen, Xin Chen, Xun Chen, Zehui Chen, Zhi Chen, Pei Chu, Xiaoyi Dong, Haodong Duan, Qi Fan, Zhaoye Fei, Yang Gao, Jiaye Ge, Chenya Gu, Yuzhe Gu, Tao Gui, Aijia Guo, Qipeng Guo, Conghui He, Yingfan Hu, Ting Huang, Tao Jiang, Penglong Jiao, Zhenjiang Jin, Zhikai Lei, Jiaxing Li, Jingwen Li, Linyang Li, Shuaibin Li, Wei Li, Yining Li, Hongwei Liu, Jiangning Liu, Jiawei Hong, Kaiwen Liu, Kuikun Liu, Xiaoran Liu, Chengqi Lv, Haijun Lv, Kai Lv, Li Ma, Runyuan Ma, Zerun Ma, Wenchang Ning, Linke Ouyang, Jiantao Qiu, Yuan Qu, FuKai Shang, Yunfan Shao, Demin Song, Zifan Song, Zhihao Sui, Peng Sun, Yu Sun, Huanze Tang, Bin Wang, Guoteng Wang, Jiaqi Wang, Jiayu Wang, Rui Wang, Yudong Wang, Ziyi Wang, Xingjian Wei, Qizhen Weng, Fan Wu, Yingtong Xiong, Chao Xu, Ruiliang Xu, Hang Yan, Yirong Yan, Xiaogui Yang, Haochen Ye, Huaiyuan Ying, JIA YU, Jing Yu, Yuhang Zang, Chuyu Zhang, Li Zhang, Pan Zhang, Peng Zhang, Ruijie Zhang, Shuo Zhang, Songyang Zhang, Wenjian Zhang, Wenwei Zhang, Xingcheng Zhang, Xinyue Zhang, Hui Zhao, Qian Zhao, Xiaomeng Zhao, Fengzhe Zhou, Zaida Zhou, Jingming Zhuo, Yicheng Zou, Xipeng Qiu, Yu Qiao, Dahua Lin
The evolution of Large Language Models (LLMs) like ChatGPT and GPT-4 has sparked discussions on the advent of Artificial General Intelligence (AGI).
Ranked #5 on Long-Context Understanding on Ada-LEval (BestAnswer)
1 code implementation • 25 Mar 2024 • Lingdong Kong, Xiang Xu, Jun Cen, Wenwei Zhang, Liang Pan, Kai Chen, Ziwei Liu
Safety-critical 3D scene understanding tasks necessitate not only accurate but also confident predictions from 3D perception models.
no code implementations • 25 Mar 2024 • Junshu Tang, Yanhong Zeng, Ke Fan, Xuheng Wang, Bo Dai, Kai Chen, Lizhuang Ma
Creating and animating 3D biped cartoon characters is crucial and valuable in various applications.
no code implementations • 20 Mar 2024 • Yibo Wang, Ruiyuan Gao, Kai Chen, Kaiqiang Zhou, Yingjie Cai, Lanqing Hong, Zhenguo Li, Lihui Jiang, Dit-yan Yeung, Qiang Xu, Kai Zhang
Furthermore, image syntheses from DetDiffusion can effectively augment training data, significantly enhancing downstream detection performance.
1 code implementation • 19 Mar 2024 • Zehui Chen, Kuikun Liu, Qiuchen Wang, Wenwei Zhang, Jiangning Liu, Dahua Lin, Kai Chen, Feng Zhao
Open-sourced Large Language Models (LLMs) have achieved great success in various NLP tasks, however, they are still far inferior to API-based models when acting as agents.
no code implementations • 14 Mar 2024 • Yunhao Gou, Kai Chen, Zhili Liu, Lanqing Hong, Hang Xu, Zhenguo Li, Dit-yan Yeung, James T. Kwok, Yu Zhang
Multimodal large language models (MLLMs) have shown impressive reasoning abilities, which, however, are also more vulnerable to jailbreak attacks than their LLM predecessors.
1 code implementation • 13 Mar 2024 • Bowen Li, Wenhan Wu, Ziwei Tang, Lin Shi, John Yang, Jinyang Li, Shunyu Yao, Chen Qian, Binyuan Hui, Qicheng Zhang, Zhiyin Yu, He Du, Ping Yang, Dahua Lin, Chao Peng, Kai Chen
Recent advancements in large language models (LLMs) have significantly enhanced their coding capabilities.
1 code implementation • 4 Mar 2024 • Xudong Liao, Han Tian, Chaoliang Zeng, Xinchen Wan, Kai Chen
We present Astraea, a new learning-based congestion control that ensures fast convergence to fairness with stability.
no code implementations • 28 Feb 2024 • Tong Liu, Yingjie Zhang, Zhe Zhao, Yinpeng Dong, Guozhu Meng, Kai Chen
We evaluate DRA across various open-source and close-source models, showcasing state-of-the-art jailbreak success rates and attack efficiency.
no code implementations • 24 Feb 2024 • Zhenhua Wang, Wei Xie, Baosheng Wang, Enze Wang, Zhiwen Gui, Shuoyoucheng Ma, Kai Chen
Our research provides a psychological explanation of the jailbreak prompts.
1 code implementation • 21 Feb 2024 • Tian Lan, Wenwei Zhang, Chen Xu, Heyan Huang, Dahua Lin, Kai Chen, Xian-Ling Mao
Critique ability are crucial in the scalable oversight and self-improvement of Large Language Models (LLMs).
1 code implementation • 18 Feb 2024 • Kai Chen, Zihao He, Jun Yan, Taiwei Shi, Kristina Lerman
Large Language Models (LLMs) possess the potential to exert substantial influence on public perceptions and interactions with information.
1 code implementation • 9 Feb 2024 • Huaiyuan Ying, Shuo Zhang, Linyang Li, Zhejian Zhou, Yunfan Shao, Zhaoye Fei, Yichuan Ma, Jiawei Hong, Kuikun Liu, Ziyi Wang, Yudong Wang, Zijian Wu, Shuaibin Li, Fengzhe Zhou, Hongwei Liu, Songyang Zhang, Wenwei Zhang, Hang Yan, Xipeng Qiu, Jiayu Wang, Kai Chen, Dahua Lin
We further explore how to use LEAN to solve math problems and study its performance under the setting of multi-task learning which shows the possibility of using LEAN as a unified platform for solving and proving in math.
no code implementations • 8 Feb 2024 • Zhili Liu, Kai Chen, Jianhua Han, Lanqing Hong, Hang Xu, Zhenguo Li, James T. Kwok
It also obtains new state-of-the-art self-supervised learning results on detection and segmentation.
1 code implementation • 29 Jan 2024 • Xiaoyi Dong, Pan Zhang, Yuhang Zang, Yuhang Cao, Bin Wang, Linke Ouyang, Xilin Wei, Songyang Zhang, Haodong Duan, Maosong Cao, Wenwei Zhang, Yining Li, Hang Yan, Yang Gao, Xinyue Zhang, Wei Li, Jingwen Li, Kai Chen, Conghui He, Xingcheng Zhang, Yu Qiao, Dahua Lin, Jiaqi Wang
We introduce InternLM-XComposer2, a cutting-edge vision-language model excelling in free-form text-image composition and comprehension.
Ranked #17 on Visual Question Answering on MM-Vet
1 code implementation • 26 Jan 2024 • Peizhuo Lv, Hualong Ma, Kai Chen, Jiachen Zhou, Shengzhi Zhang, Ruigang Liang, Shenchen Zhu, Pan Li, Yingjun Zhang
To protect the Intellectual Property (IP) of the original owners over such DNN models, backdoor-based watermarks have been extensively studied.
1 code implementation • 24 Jan 2024 • Qinyuan Cheng, Tianxiang Sun, Xiangyang Liu, Wenwei Zhang, Zhangyue Yin, ShiMin Li, Linyang Li, Zhengfu He, Kai Chen, Xipeng Qiu
To answer this question, we construct a model-specific "I don't know" (Idk) dataset for an assistant, which contains its known and unknown questions, based on existing open-domain question answering datasets.
no code implementations • 24 Jan 2024 • Yanyan Yang, Lili Wang, Xiaoya Zhai, Kai Chen, WenMing Wu, Yunkai Zhao, Ligang Liu, Xiao-Ming Fu
Mechanical metamaterial is a synthetic material that can possess extraordinary physical characteristics, such as abnormal elasticity, stiffness, and stability, by carefully designing its internal structure.
no code implementations • 18 Jan 2024 • Jianzong Wu, Xiangtai Li, Chenyang Si, Shangchen Zhou, Jingkang Yang, Jiangning Zhang, Yining Li, Kai Chen, Yunhai Tong, Ziwei Liu, Chen Change Loy
We introduce a new task -- language-driven video inpainting, which uses natural language instructions to guide the inpainting process.
1 code implementation • 18 Jan 2024 • Xiangtai Li, Haobo Yuan, Wei Li, Henghui Ding, Size Wu, Wenwei Zhang, Yining Li, Kai Chen, Chen Change Loy
In this work, we address various segmentation tasks, each traditionally tackled by distinct or partially unified models.
1 code implementation • 18 Jan 2024 • Shilin Xu, Haobo Yuan, Qingyu Shi, Lu Qi, Jingbo Wang, Yibo Yang, Yining Li, Kai Chen, Yunhai Tong, Bernard Ghanem, Xiangtai Li, Ming-Hsuan Yang
Segment Anything Model (SAM) is one remarkable model that can achieve generalized segmentation.
1 code implementation • 16 Jan 2024 • Huanjun Kong, Songyang Zhang, Jiaying Li, Min Xiao, Jun Xu, Kai Chen
In this work, we present HuixiangDou, a technical assistant powered by Large Language Models (LLM).
1 code implementation • 8 Jan 2024 • Yueqian Wang, Yuxuan Wang, Kai Chen, Dongyan Zhao
However, most models can only handle simple videos in terms of temporal reasoning, and their performance tends to drop when answering temporal-reasoning questions on long and informative videos.
1 code implementation • 5 Jan 2024 • Haobo Yuan, Xiangtai Li, Chong Zhou, Yining Li, Kai Chen, Chen Change Loy
The CLIP and Segment Anything Model (SAM) are remarkable vision foundation models (VFMs).
no code implementations • 28 Dec 2023 • Chuan Wen, Xingyu Lin, John So, Kai Chen, Qi Dou, Yang Gao, Pieter Abbeel
Learning from demonstration is a powerful method for teaching robots new skills, and having more demonstration data often improves policy learning.
no code implementations • 27 Dec 2023 • Jinwen He, Yujia Gong, Kai Chen, Zijin Lin, Chengan Wei, Yue Zhao
In this paper, we introduce the LLM factoscope, a novel Siamese network-based model that leverages the inner states of LLMs for factual detection.
1 code implementation • 26 Dec 2023 • Tai Wang, Xiaohan Mao, Chenming Zhu, Runsen Xu, Ruiyuan Lyu, Peisen Li, Xiao Chen, Wenwei Zhang, Kai Chen, Tianfan Xue, Xihui Liu, Cewu Lu, Dahua Lin, Jiangmiao Pang
In the realm of computer vision and robotics, embodied agents are expected to explore their environment and carry out human instructions.
1 code implementation • 21 Dec 2023 • Zehui Chen, Weihua Du, Wenwei Zhang, Kuikun Liu, Jiangning Liu, Miao Zheng, Jingming Zhuo, Songyang Zhang, Dahua Lin, Kai Chen, Feng Zhao
Based on that, we further introduce T-Eval to evaluate the tool utilization capability step by step.
1 code implementation • 21 Dec 2023 • Yiming Zhang, Zhening Xing, Yanhong Zeng, Youqing Fang, Kai Chen
Recent advancements in personalized text-to-image (T2I) models have revolutionized content creation, empowering non-experts to generate stunning images with unique styles.
no code implementations • 19 Dec 2023 • Yunhao Gou, Zhili Liu, Kai Chen, Lanqing Hong, Hang Xu, Aoxue Li, Dit-yan Yeung, James T. Kwok, Yu Zhang
Instruction tuning of Large Vision-language Models (LVLMs) has revolutionized the development of versatile models with zero-shot generalization across a wide range of downstream vision-language tasks.
1 code implementation • 18 Dec 2023 • Jiachen Zhou, Peizhuo Lv, Yibing Lan, Guozhu Meng, Kai Chen, Hualong Ma
Dataset sanitization is a widely adopted proactive defense against poisoning-based backdoor attacks, aimed at filtering out and removing poisoned samples from training datasets.
1 code implementation • 12 Dec 2023 • Peng Lu, Tao Jiang, Yining Li, Xiangtai Li, Kai Chen, Wenming Yang
Real-time multi-person pose estimation presents significant challenges in balancing speed and precision.
Ranked #1 on Multi-Person Pose Estimation on CrowdPose (using extra training data)
1 code implementation • 12 Dec 2023 • Zeming Chen, Wenwei Zhang, Xinjiang Wang, Kai Chen, Zhi Wang
While the pseudo-label method has demonstrated considerable success in semi-supervised object detection tasks, this paper uncovers notable limitations within this approach.
Ranked #1 on Semi-Supervised Object Detection on COCO 100% labeled data (using extra training data)
1 code implementation • 6 Dec 2023 • Junhao Zhuang, Yanhong Zeng, Wenran Liu, Chun Yuan, Kai Chen
This enables PowerPaint to accomplish various inpainting tasks by utilizing different task prompts, resulting in state-of-the-art performance.
no code implementations • 1 Dec 2023 • Pengxiang Li, Kai Chen, Zhili Liu, Ruiyuan Gao, Lanqing Hong, Guo Zhou, Hua Yao, Dit-yan Yeung, Huchuan Lu, Xu Jia
Despite remarkable achievements in video synthesis, achieving granular control over complex dynamics, such as nuanced movement among multiple interacting objects, still presents a significant hurdle for dynamic world modeling, compounded by the necessity to manage appearance and disappearance, drastic scale changes, and ensure consistency for instances across frames.
1 code implementation • 15 Nov 2023 • Taiwei Shi, Kai Chen, Jieyu Zhao
To verify the effectiveness of Safer-Instruct, we apply the pipeline to construct a safety preference dataset as a case study.
1 code implementation • 14 Nov 2023 • Yinuo Wang, Kai Chen, Weimin Yuan, Cai Meng, Xiangzhi Bai
Segment Anything Model (SAM), a vision foundation model trained on large-scale annotations, has recently continued raising awareness within medical image segmentation.
1 code implementation • 20 Oct 2023 • Haodong Duan, Jueqi Wei, Chonghua Wang, Hongwei Liu, Yixiao Fang, Songyang Zhang, Dahua Lin, Kai Chen
In contrast, other LLMs struggle to generate multi-turn dialogues of satisfactory quality due to poor instruction-following capability, tendency to generate lengthy utterances, or limited general capability.
no code implementations • 16 Oct 2023 • Kai Chen, Chunwei Wang, Kuo Yang, Jianhua Han, Lanqing Hong, Fei Mi, Hang Xu, Zhengying Liu, Wenyong Huang, Zhenguo Li, Dit-yan Yeung, Lifeng Shang, Xin Jiang, Qun Liu
The rapid development of large language models (LLMs) has not only provided numerous opportunities but also presented significant challenges.
no code implementations • 9 Oct 2023 • Zhili Liu, Kai Chen, Yifan Zhang, Jianhua Han, Lanqing Hong, Hang Xu, Zhenguo Li, Dit-yan Yeung, James Kwok
To address this, we utilize the intrinsic geometric characteristics of implicit concepts and present the Geom-Erasing, a novel concept removal method based on geometric-driven control.
2 code implementations • 5 Oct 2023 • Qinyuan Cheng, Tianxiang Sun, Wenwei Zhang, Siyin Wang, Xiangyang Liu, Mozhi Zhang, Junliang He, Mianqiu Huang, Zhangyue Yin, Kai Chen, Xipeng Qiu
We analyze the primary types of hallucinations in different types of models and their causes.
no code implementations • 4 Oct 2023 • Ruiyuan Gao, Kai Chen, Enze Xie, Lanqing Hong, Zhenguo Li, Dit-yan Yeung, Qiang Xu
Recent advancements in diffusion models have significantly enhanced the data synthesis with 2D control.
1 code implementation • 28 Sep 2023 • Zhiwei Fei, Xiaoyu Shen, Dawei Zhu, Fengzhe Zhou, Zhuo Han, Songyang Zhang, Kai Chen, Zongwen Shen, Jidong Ge
We hope this benchmark provides in-depth understanding of the LLMs' domain-specified capabilities and speed up the development of LLMs in the legal domain.
1 code implementation • 26 Sep 2023 • Pan Zhang, Xiaoyi Dong, Bin Wang, Yuhang Cao, Chao Xu, Linke Ouyang, Zhiyuan Zhao, Haodong Duan, Songyang Zhang, Shuangrui Ding, Wenwei Zhang, Hang Yan, Xinyue Zhang, Wei Li, Jingwen Li, Kai Chen, Conghui He, Xingcheng Zhang, Yu Qiao, Dahua Lin, Jiaqi Wang
We propose InternLM-XComposer, a vision-language large model that enables advanced image-text comprehension and composition.
Ranked #9 on Visual Question Answering (VQA) on InfiMM-Eval
no code implementations • 18 Sep 2023 • Chenming Zhu, Wenwei Zhang, Tai Wang, Xihui Liu, Kai Chen
Instead of leveraging 2D images, we propose Object2Scene, the first approach that leverages large-scale large-vocabulary 3D object datasets to augment existing 3D scene datasets for open-vocabulary 3D object detection.
1 code implementation • 9 Sep 2023 • Jinwen He, Kai Chen, Guozhu Meng, Jiangshan Zhang, Congyi Li
While enjoying the great achievements brought by deep learning (DL), people are also worried about the decision made by DL models, since the high degree of non-linearity of DL models makes the decision extremely difficult to understand.
no code implementations • 2 Sep 2023 • Jiaqi Liu, Yonghao Long, Kai Chen, Cheuk Hei Leung, Zerui Wang, Qi Dou
However, this task is very challenging due to the small sizes of surgical instrument tips, and significant variance of surgical scenes across different procedures.
1 code implementation • 23 Aug 2023 • Di Chai, Leye Wang, Liu Yang, Junxue Zhang, Kai Chen, Qiang Yang
Evaluation is a systematic approach to assessing how well a system achieves its intended purpose.
no code implementations • 16 Aug 2023 • Zhenhua Wang, Wei Xie, Kai Chen, Baosheng Wang, Zhiwen Gui, Enze Wang
Inspired by the attack that penetrates traditional firewalls through reverse tunnels, we introduce a "self-deception" attack that can bypass the semantic firewall by inducing LLM to generate prompts that facilitate jailbreak.
1 code implementation • ICCV 2023 • Jun Zhou, Kai Chen, Linlin Xu, Qi Dou, Jing Qin
One critical challenge in 6D object pose estimation from a single RGBD image is efficient integration of two different modalities, i. e., color and depth.
1 code implementation • 5 Aug 2023 • Yong liu, Hang Dong, Boyang Liang, Songwei Liu, Qingji Dong, Kai Chen, Fangmin Chen, Lean Fu, Fei Wang
Since the high resolution of intermediate features in SISR models increases memory and computational requirements, efficient SISR transformers are more favored.
1 code implementation • KDD 2023 • Yilun Jin, Kai Chen, Qiang Yang
To address the problem, we propose TransGTR, a transferable structure learning framework for traffic forecasting that jointly learns and transfers the graph structures and forecasting models across cities.
no code implementations • 4 Aug 2023 • Wangbo Zhao, Kepan Nan, Songyang Zhang, Kai Chen, Dahua Lin, Yang You
Based on this scheme, we develop a novel RVOS method that exploits weak annotations effectively.
1 code implementation • ICCV 2023 • YuAn Liu, Songyang Zhang, Jiacheng Chen, Zhaohui Yu, Kai Chen, Dahua Lin
There has been significant progress in Masked Image Modeling (MIM).
1 code implementation • 1 Aug 2023 • Jinglei Zhang, Tiancheng Lin, Yi Xu, Kai Chen, Rui Zhang
We argue that such prior contextual information can be interpreted as the relations of textual primitives due to the heterogeneous text and background, which can provide effective self-supervised labels for representation learning.
1 code implementation • 31 Jul 2023 • Tao Huang, Kai Chen, Wang Wei, Jianan Li, Yonghao Long, Qi Dou
Based on this value function, a chaining policy is learned to instruct subtask policies to terminate at the state with the highest value so that all subsequent policies are more likely to be connected for accomplishing the task.
3 code implementations • 12 Jul 2023 • YuAn Liu, Haodong Duan, Yuanhan Zhang, Bo Li, Songyang Zhang, Wangbo Zhao, Yike Yuan, Jiaqi Wang, Conghui He, Ziwei Liu, Kai Chen, Dahua Lin
In response to these challenges, we propose MMBench, a novel multi-modality benchmark.
Ranked #1 on Visual Question Answering on MMBench
no code implementations • 11 Jul 2023 • Zhao Liu, Quanchen Zou, Tian Yu, Xuan Wang, Guozhu Meng, Kai Chen, Deyue Zhang
Guided by the constraints, ConFL is able to generate valid inputs that can pass the verification and explore deeper paths of kernel codes.
2 code implementations • 7 Jul 2023 • Shilong Zhang, Peize Sun, Shoufa Chen, Min Xiao, Wenqi Shao, Wenwei Zhang, Yu Liu, Kai Chen, Ping Luo
Before sending to LLM, the reference is replaced by RoI features and interleaved with language embeddings as a sequence.
Ranked #1 on Visual Question Answering (VQA) on VCR (Q-AR) test
2 code implementations • NeurIPS 2023 • Youquan Liu, Lingdong Kong, Jun Cen, Runnan Chen, Wenwei Zhang, Liang Pan, Kai Chen, Ziwei Liu
Recent advancements in vision foundation models (VFMs) have opened up new possibilities for versatile and efficient visual perception.
no code implementations • 7 Jun 2023 • Kai Chen, Enze Xie, Zhe Chen, Yibo Wang, Lanqing Hong, Zhenguo Li, Dit-yan Yeung
Diffusion models have attracted significant attention due to the remarkable ability to create content and generate data for tasks like image classification.
no code implementations • 31 May 2023 • Haisong Ding, Bozhi Luan, Dongnan Gui, Kai Chen, Qiang Huo
This model conditions on a printed glyph image and creates mappings between printed characters and handwritten images, thus enabling the generation of photo-realistic handwritten samples with diverse styles and unseen text contents.
1 code implementation • NeurIPS 2023 • Yukang Yang, Dongnan Gui, Yuhui Yuan, Weicong Liang, Haisong Ding, Han Hu, Kai Chen
We evaluate the effectiveness of our approach by measuring OCR-based metrics, CLIP score, and FID of the generated visual text.
no code implementations • 28 May 2023 • Xiaojin Zhang, Yan Kang, Lixin Fan, Kai Chen, Qiang Yang
Motivated by this requirement, we propose a framework that (1) formulates TFL as a problem of finding a protection mechanism to optimize the tradeoff between privacy leakage, utility loss, and efficiency reduction and (2) formally defines bounded measurements of the three factors.
1 code implementation • 26 May 2023 • Jiduan Liu, Jiahao Liu, Qifan Wang, Jingang Wang, Wei Wu, Yunsen Xian, Dongyan Zhao, Kai Chen, Rui Yan
In this paper, we propose a novel approach, RankCSE, for unsupervised sentence representation learning, which incorporates ranking consistency and ranking distillation with contrastive learning into a unified framework.
no code implementations • 25 May 2023 • Dongnan Gui, Kai Chen, Haisong Ding, Qiang Huo
Training from handwritten samples of a small character set, the DDPM is capable of mapping printed strokes to handwritten ones, which makes it possible to generate photo-realistic and diverse style handwritten samples of unseen character categories.
no code implementations • 24 May 2023 • Xiaojin Zhang, Wenjie Li, Kai Chen, Shutao Xia, Qiang Yang
We propose a general learning framework for the protection mechanisms that protects privacy via distorting model parameters, which facilitates the trade-off between privacy and utility.
no code implementations • 17 May 2023 • Hao Li, Peng Jin, Zesen Cheng, Songyang Zhang, Kai Chen, Zhennan Wang, Chang Liu, Jie Chen
Video question answering aims at answering a question about the video content by reasoning the alignment semantics within them.
1 code implementation • 8 May 2023 • Tao Gong, Chengqi Lyu, Shilong Zhang, Yudong Wang, Miao Zheng, Qian Zhao, Kuikun Liu, Wenwei Zhang, Ping Luo, Kai Chen
To further enhance the ability to chat with humans of the MultiModal-GPT, we utilize language-only instruction-following data to train the MultiModal-GPT jointly.
no code implementations • 7 May 2023 • Xiaojin Zhang, Kai Chen, Qiang Yang
The nature of the widely-adopted protection mechanisms including \textit{Randomization Mechanism} and \textit{Compression Mechanism} is to protect privacy via distorting model parameter.
no code implementations • 29 Apr 2023 • Yan Kang, Hanlin Gu, Xingxing Tang, Yuanqin He, Yuzhu Zhang, Jinnan He, Yuxing Han, Lixin Fan, Kai Chen, Qiang Yang
Different from existing CMOFL works focusing on utility, efficiency, fairness, and robustness, we consider optimizing privacy leakage along with utility loss and training cost, the three primary objectives of a TFL system.
2 code implementations • 19 Apr 2023 • Xiangtai Li, Henghui Ding, Haobo Yuan, Wenwei Zhang, Jiangmiao Pang, Guangliang Cheng, Kai Chen, Ziwei Liu, Chen Change Loy
Recently, transformers, a type of neural network based on self-attention originally designed for natural language processing, have considerably surpassed previous convolutional or recurrent approaches in various vision processing tasks.
1 code implementation • 13 Apr 2023 • Shaoyuan Xie, Lingdong Kong, Wenwei Zhang, Jiawei Ren, Liang Pan, Kai Chen, Ziwei Liu
Our experiments further demonstrate that pre-training and depth-free BEV transformation has the potential to enhance out-of-distribution robustness.
2 code implementations • 12 Apr 2023 • Jiahao Wang, Songyang Zhang, Yong liu, Taiqiang Wu, Yujiu Yang, Xihui Liu, Kai Chen, Ping Luo, Dahua Lin
Extensive experiments and ablative analysis also demonstrate that the inductive bias of network architecture, can be incorporated into simple network structure with appropriate optimization strategy.
no code implementations • 11 Apr 2023 • Xiaojin Zhang, Lixin Fan, Siwei Wang, Wenjie Li, Kai Chen, Qiang Yang
To address this, we propose the first game-theoretic framework that considers both FL defenders and attackers in terms of their respective payoffs, which include computational costs, FL model utilities, and privacy leakage risks.
no code implementations • 10 Apr 2023 • Xiaojin Zhang, Anbu Huang, Lixin Fan, Kai Chen, Qiang Yang
However, existing multi-objective optimization frameworks are very time-consuming, and do not guarantee the existence of the Pareto frontier, this motivates us to seek a solution to transform the multi-objective problem into a single-objective problem because it is more efficient and easier to be solved.
no code implementations • 4 Apr 2023 • Liu Yang, Di Chai, Junxue Zhang, Yilun Jin, Leye Wang, Hao liu, Han Tian, Qian Xu, Kai Chen
From the hardware layer to the vertical federated system layer, researchers contribute to various aspects of VFL.
1 code implementation • CVPR 2023 • Kai Chen, Zhili Liu, Lanqing Hong, Hang Xu, Zhenguo Li, Dit-yan Yeung
Specifically, our MixedAE outperforms MAE by +0. 3% accuracy, +1. 7 mIoU and +0. 9 AP on ImageNet-1K, ADE20K and COCO respectively with a standard ViT-Base.
1 code implementation • ICCV 2023 • Lingdong Kong, Youquan Liu, Xin Li, Runnan Chen, Wenwei Zhang, Jiawei Ren, Liang Pan, Kai Chen, Ziwei Liu
The robustness of 3D perception systems under natural corruptions from environments and sensors is pivotal for safety-critical applications.
no code implementations • 25 Mar 2023 • Yilun Jin, Yang Liu, Kai Chen, Qiang Yang
Therefore, the problem of federated learning without full labels is important in real-world FL applications.
1 code implementation • CVPR 2023 • Shilong Zhang, Xinjiang Wang, Jiaqi Wang, Jiangmiao Pang, Chengqi Lyu, Wenwei Zhang, Ping Luo, Kai Chen
Concretely, we first lay dense queries like traditional detectors and then select distinct ones for one-to-one assignments.
Ranked #3 on Object Detection on CrowdHuman (full body)
no code implementations • ICCV 2023 • Tianhang Wang, Guang Chen, Kai Chen, Zhengfa Liu, Bo Zhang, Alois Knoll, Changjun Jiang
To verify our algorithm, we conducted experiments on the V2X-Sim and OPV2V datasets.
1 code implementation • 13 Mar 2023 • Tao Jiang, Peng Lu, Li Zhang, Ningsheng Ma, Rui Han, Chengqi Lyu, Yining Li, Kai Chen
Recent studies on 2D pose estimation have achieved excellent performance on public benchmarks, yet its application in the industrial community still suffers from heavy model parameters and high latency.
Ranked #3 on Pose Estimation on OCHuman (using extra training data)
no code implementations • 11 Mar 2023 • Zhao Yang, Jiaqi Wang, Yansong Tang, Kai Chen, Hengshuang Zhao, Philip H. S. Torr
Referring image segmentation segments an image from a language expression.
1 code implementation • 4 Mar 2023 • YuAn Liu, Songyang Zhang, Jiacheng Chen, Kai Chen, Dahua Lin
Masked Image Modeling (MIM) has achieved promising progress with the advent of Masked Autoencoders (MAE) and BEiT.
2 code implementations • 20 Feb 2023 • Tao Huang, Kai Chen, Bin Li, Yun-hui Liu, Qi Dou
Task automation of surgical robot has the potentials to improve surgical efficiency.
no code implementations • 3 Jan 2023 • Ying Cao, Ruigang Liang, Kai Chen, Peiwei Hu
They formulate the decompilation process as a translation problem between LPL and HPL, aiming to reduce the human cost required to develop decompilation tools and improve their generalizability.
1 code implementation • ICCV 2023 • Xiaoyang Huang, Yi Zhang, Kai Chen, Teng Li, Wenjun Zhang, Bingbing Ni
In this work, a novel regularization term named Implicit Convexity Regularization (ICR) imposed on implicit primitive learning is proposed to tackle this problem.
no code implementations • CVPR 2023 • Jiahao Wang, Songyang Zhang, Yong liu, Taiqiang Wu, Yujiu Yang, Xihui Liu, Kai Chen, Ping Luo, Dahua Lin
Extensive experiments and ablative analysis also demonstrate that the inductive bias of network architecture, can be incorporated into simple network structure with appropriate optimization strategy.
9 code implementations • 14 Dec 2022 • Chengqi Lyu, Wenwei Zhang, Haian Huang, Yue Zhou, Yudong Wang, Yanyi Liu, Shilong Zhang, Kai Chen
In this paper, we aim to design an efficient real-time object detector that exceeds the YOLO series and is easily extensible for many object recognition tasks such as instance segmentation and rotated object detection.
Ranked #1 on Oriented Object Detection on DOTA 1.5
no code implementations • 1 Dec 2022 • Kai Chen, Zihao He, Rong-Ching Chang, Jonathan May, Kristina Lerman
We collect discussions from a wide variety of topical forums and use emotion detection to recognize a range of emotions from text, including anger, fear, joy, admiration, etc.
no code implementations • 3 Nov 2022 • Kai Chen, Stephen James, Congying Sui, Yun-hui Liu, Pieter Abbeel, Qi Dou
To further improve the performance of the stereo framework, StereoPose is equipped with a parallax attention module for stereo feature fusion and an epipolar loss for improving the stereo-view consistency of network predictions.
1 code implementation • 27 Oct 2022 • Xiaoyang Huang, Yi Zhang, Bingbing Ni, Teng Li, Kai Chen, Wenjun Zhang
In this work, we focus on boosting the image quality of point clouds rendering with a compact model design.
no code implementations • 17 Oct 2022 • Pan Li, Peizhuo Lv, Shenchen Zhu, Ruigang Liang, Kai Chen
Although traditional static DNNs are vulnerable to the membership inference attack (MIA) , which aims to infer whether a particular point was used to train the model, little is known about how such an attack performs on the dynamic NNs.
3 code implementations • 12 Oct 2022 • Haodong Duan, Jiaqi Wang, Kai Chen, Dahua Lin
Graph convolution networks (GCN) have been widely used in skeleton-based action recognition.
Ranked #7 on Skeleton Based Action Recognition on NTU RGB+D
1 code implementation • 20 Sep 2022 • Haodong Duan, Yue Zhao, Kai Chen, Yuanjun Xiong, Dahua Lin
Deep learning models have achieved excellent recognition results on large-scale video benchmarks.
1 code implementation • 16 Sep 2022 • Lin Chen, Zhixiang Wei, Xin Jin, Huaian Chen, Miao Zheng, Kai Chen, Yi Jin
In this work, we resort to data mixing to establish a deliberated domain bridging (DDB) for DASS, through which the joint distributions of source and target domains are aligned and interacted with each in the intermediate space.
Ranked #1 on Domain Adaptation on GTAV+Synscapes to Cityscapes
1 code implementation • 8 Sep 2022 • Peizhuo Lv, Pan Li, Shenchen Zhu, Shengzhi Zhang, Kai Chen, Ruigang Liang, Chang Yue, Fan Xiang, Yuling Cai, Hualong Ma, Yingjun Zhang, Guozhu Meng
Recent years have witnessed tremendous success in Self-Supervised Learning (SSL), which has been widely utilized to facilitate various downstream tasks in Computer Vision (CV) and Natural Language Processing (NLP) domains.
1 code implementation • CVPR 2023 • Xinjiang Wang, Xingyi Yang, Shilong Zhang, Yijiang Li, Litong Feng, Shijie Fang, Chengqi Lyu, Kai Chen, Wayne Zhang
In this study, we dive deep into the inconsistency of pseudo targets in semi-supervised object detection (SSOD).
no code implementations • 1 Sep 2022 • Xiaojin Zhang, Yan Kang, Kai Chen, Lixin Fan, Qiang Yang
In addition, it is a mandate for a federated learning system to achieve high \textit{efficiency} in order to enable large-scale model training and deployment.
no code implementations • 9 Jul 2022 • Chang Yue, Peizhuo Lv, Ruigang Liang, Kai Chen
However, most of the triggers used in the current study are fixed patterns patched on a small fraction of an image and are often clearly mislabeled, which is easily detected by humans or defense methods such as Neural Cleanse and SentiNet.
1 code implementation • 4 Jul 2022 • Guoliang Cheng, Lele Liao, Kai Chen, Yuxiang Hu, Changbao Zhu, Jing Lu
The recently proposed semi-blind source separation (SBSS) method for nonlinear acoustic echo cancellation (NAEC) outperforms adaptive NAEC in attenuating the nonlinear acoustic echo.
no code implementations • 28 Jun 2022 • Shuowei Cai, Di Chai, Liu Yang, Junxue Zhang, Yilun Jin, Leye Wang, Kun Guo, Kai Chen
In this paper, we focus on SplitNN, a well-known neural network framework in VFL, and identify a trade-off between data security and model performance in SplitNN.
no code implementations • 23 Jun 2022 • Jing Tan, Lars Braubach, Kai Jander, Rongjun Xu, Kai Chen
The system has been implemented as proof of concept and is currently reimplemented and transferred to a production system based on the Jadex agent platform.
1 code implementation • 2 Jun 2022 • Shilong Zhang, Xinjiang Wang, Jiaqi Wang, Jiangmiao Pang, Kai Chen
As both sparse and dense queries are imperfect, then \emph{what are expected queries in end-to-end object detection}?
no code implementations • 26 May 2022 • Zhili Liu, Jianhua Han, Lanqing Hong, Hang Xu, Kai Chen, Chunjing Xu, Zhenguo Li
On the other hand, for existing SSL methods, it is burdensome and infeasible to use different downstream-task-customized datasets in pre-training for different tasks.
1 code implementation • 19 May 2022 • Haodong Duan, Jiaqi Wang, Kai Chen, Dahua Lin
The toolbox supports a wide variety of skeleton action recognition algorithms, including approaches based on GCN and CNN.
Ranked #19 on Skeleton Based Action Recognition on NTU RGB+D 120
1 code implementation • CVPR 2022 • Shilong Zhang, Zhuoran Yu, Liyang Liu, Xinjiang Wang, Aojun Zhou, Kai Chen
The core of this task is to train a point-to-box regressor on well-labeled images that can be used to predict credible bounding boxes for each point annotation.
1 code implementation • CVPR 2022 • Haodong Duan, Nanxuan Zhao, Kai Chen, Dahua Lin
To mitigate this problem, we developed TransRank, a unified framework for recognizing Transformations in a Ranking formulation.
1 code implementation • 28 Apr 2022 • Yue Zhou, Xue Yang, Gefan Zhang, Jiabao Wang, Yanyi Liu, Liping Hou, Xue Jiang, Xingzhao Liu, Junchi Yan, Chengqi Lyu, Wenwei Zhang, Kai Chen
We present an open-source toolbox, named MMRotate, which provides a coherent algorithm framework of training, inferring, and evaluation for the popular rotated object detection algorithm based on deep learning.
no code implementations • 26 Apr 2022 • Zhenjie Yu, Kai Chen, Shuang Li, Bingfeng Han, Chi Harold Liu, Shuigen Wang
To be specific, ROMA could efficiently translate the unpaired nighttime infrared videos into fine-grained daytime visible ones, meanwhile maintain the spatiotemporal consistency via matching the cross-domain region similarity.
2 code implementations • 20 Apr 2022 • Ren Yang, Radu Timofte, Meisong Zheng, Qunliang Xing, Minglang Qiao, Mai Xu, Lai Jiang, Huaida Liu, Ying Chen, Youcheng Ben, Xiao Zhou, Chen Fu, Pei Cheng, Gang Yu, Junyi Li, Renlong Wu, Zhilu Zhang, Wei Shang, Zhengyao Lv, Yunjin Chen, Mingcai Zhou, Dongwei Ren, Kai Zhang, WangMeng Zuo, Pavel Ostyakov, Vyal Dmitry, Shakarim Soltanayev, Chervontsev Sergey, Zhussip Magauiya, Xueyi Zou, Youliang Yan, Pablo Navarrete Michelini, Yunhua Lu, Diankai Zhang, Shaoli Liu, Si Gao, Biao Wu, Chengjian Zheng, Xiaofeng Zhang, Kaidi Lu, Ning Wang, Thuong Nguyen Canh, Thong Bach, Qing Wang, Xiaopeng Sun, Haoyu Ma, Shijie Zhao, Junlin Li, Liangbin Xie, Shuwei Shi, Yujiu Yang, Xintao Wang, Jinjin Gu, Chao Dong, Xiaodi Shi, Chunmei Nian, Dong Jiang, Jucai Lin, Zhihuai Xie, Mao Ye, Dengyan Luo, Liuhan Peng, Shengjie Chen, Qian Wang, Xin Liu, Boyang Liang, Hang Dong, Yuhao Huang, Kai Chen, Xingbei Guo, Yujing Sun, Huilei Wu, Pengxu Wei, Yulin Huang, Junying Chen, Ik Hyun Lee, Sunder Ali Khowaja, Jiseok Yoon
This challenge includes three tracks.
no code implementations • 14 Apr 2022 • Kai Chen, Rui Cao, Stephen James, Yichuan Li, Yun-hui Liu, Pieter Abbeel, Qi Dou
To continuously improve the quality of pseudo labels, we iterate the above steps by taking the trained student model as a new teacher and re-label real data using the refined teacher model.
1 code implementation • CVPR 2022 • Xiangtai Li, Wenwei Zhang, Jiangmiao Pang, Kai Chen, Guangliang Cheng, Yunhai Tong, Chen Change Loy
We hope this simple, yet effective method can serve as a new, flexible baseline in unified video segmentation design.
Ranked #1 on Video Panoptic Segmentation on KITTI-STEP (using extra training data)
no code implementations • 23 Mar 2022 • Fangjian Lin, Zhanhao Liang, Sitong Wu, Junjun He, Kai Chen, Shengwei Tian
In previous deep-learning-based methods, semantic segmentation has been regarded as a static or dynamic per-pixel classification task, \textit{i. e.,} classify each pixel representation to a specific category.
1 code implementation • 21 Mar 2022 • Wenwei Zhang, Jiangmiao Pang, Kai Chen, Chen Change Loy
It also extracts a batch of region embeddings that correspond to some sub-regions in the overlapped area to be contrasted for region consistency.
Ranked #2 on Unsupervised Semantic Segmentation on COCO-All (mIoU metric)
no code implementations • 15 Mar 2022 • Yangming Shi, Haisong Ding, Kai Chen, Qiang Huo
Style-guided text image generation tries to synthesize text image by imitating reference image's appearance while keeping text content unaltered.
no code implementations • 15 Mar 2022 • Kaican Li, Kai Chen, Haoyu Wang, Lanqing Hong, Chaoqiang Ye, Jianhua Han, Yukuai Chen, Wei zhang, Chunjing Xu, Dit-yan Yeung, Xiaodan Liang, Zhenguo Li, Hang Xu
One main reason that impedes the development of truly reliably self-driving systems is the lack of public datasets for evaluating the performance of object detectors on corner cases.
no code implementations • ACL 2022 • Kai Chen, Ye Wang, Yitong Li, Aiping Li
Temporal factors are tied to the growth of facts in realistic applications, such as the progress of diseases and the development of political situation, therefore, research on Temporal Knowledge Graph (TKG) attracks much attention.
Ranked #3 on Link Prediction on GDELT
no code implementations • CVPR 2022 • Jingwen He, Wu Shi, Kai Chen, Lean Fu, Chao Dong
The style modulation aims to generate realistic face details and the feature modulation dynamically fuses the multi-level encoded features and the generated ones conditioned on the upscaling factor.
no code implementations • 11 Mar 2022 • Xiaojin Zhang, Hanlin Gu, Lixin Fan, Kai Chen, Qiang Yang
In a federated learning scenario where multiple parties jointly learn a model from their respective data, there exist two conflicting goals for the choice of appropriate algorithms.
no code implementations • 5 Mar 2022 • Yidan Feng, Biqi Yang, Xianzhi Li, Chi-Wing Fu, Rui Cao, Kai Chen, Qi Dou, Mingqiang Wei, Yun-hui Liu, Pheng-Ann Heng
Industrial bin picking is a challenging task that requires accurate and robust segmentation of individual object instances.
no code implementations • 10 Feb 2022 • Chunyi Zhou, Yansong Gao, Anmin Fu, Kai Chen, Zhiyang Dai, Zhi Zhang, Minhui Xue, Yuqing Zhang
By observing a user model's gradient sensitivity to a class, PPA can profile the sample proportion of the class in the user's local dataset, and thus the user's preference of the class is exposed.
no code implementations • 17 Jan 2022 • Hao Wang, Yuxuan Qin, ChonLam Lao, Yanfang Le, Wenfei Wu, Kai Chen
However, switch memory is scarce compared to the volume of gradients transmitted in distributed training.
no code implementations • 17 Jan 2022 • Yiding Wang, Decang Sun, Kai Chen, Fan Lai, Mosharaf Chowdhury
To explore this, we first introduce the notion of training plasticity to quantify the training progress of internal DNN layers.
1 code implementation • CVPR 2022 • Jintao Lin, Haodong Duan, Kai Chen, Dahua Lin, LiMin Wang
Recent works prefer to formulate frame sampling as a sequential decision task by selecting frames one by one according to their importance, while we present a new paradigm of learning instance-specific video condensation policies to select informative frames for representing the entire video only in a single step.
1 code implementation • 28 Dec 2021 • Kai Chen, Weihua Chen, Tao He, Rong Du, Fan Wang, Xiuyu Sun, Yuchen Guo, Guiguang Ding
In TAGPerson, we extract information from target scenes and use them to control our parameterized rendering process to generate target-aware synthetic images, which would hold a smaller gap to the real images in the target domain.
no code implementations • 27 Dec 2021 • Yiqing Ma, Hao Wang, Yiming Zhang, Kai Chen
ByteScheduler partitions and rearranges tensor transmissions to improve the communication efficiency of distributed Deep Neural Network (DNN) training.
1 code implementation • ACM SIGSAC Conference on Computer and Communications Security 2021 • Yue Zhao, Hong Zhu, Kai Chen, Shengzhi Zhang
With the knowledge of error-inducing neurons, we propose two methods to fix the errors: the neuron-flip and the neuron-fine-tuning.
1 code implementation • CVPR 2022 • Zhao Yang, Jiaqi Wang, Yansong Tang, Kai Chen, Hengshuang Zhao, Philip H. S. Torr
Referring image segmentation is a fundamental vision-language task that aims to segment out an object referred to by a natural language expression from an image.
1 code implementation • NeurIPS 2021 • Yuhang Cao, Jiaqi Wang, Ying Jin, Tong Wu, Kai Chen, Ziwei Liu, Dahua Lin
1) In the association step, in contrast to implicitly leveraging multiple base classes, we construct a compact novel class feature space via explicitly imitating a specific base class feature space.
1 code implementation • 22 Nov 2021 • Peizhuo Lv, Hualong Ma, Jiachen Zhou, Ruigang Liang, Kai Chen, Shengzhi Zhang, Yunfei Yang
In this paper, we propose DBIA, a novel data-free backdoor attack against the CV-oriented transformer networks, leveraging the inherent attention mechanism of transformers to generate triggers and injecting the backdoor using the poisoned surrogate dataset.
1 code implementation • 29 Oct 2021 • Kai Chen, Zhipeng Wei, Jingjing Chen, Zuxuan Wu, Yu-Gang Jiang
On both UCF-101 and HMDB-51 datasets, our BSC attack method can achieve about 90\% fooling rate when attacking three mainstream video recognition models, while only occluding \textless 8\% areas in the video.
Adversarial Attack Adversarial Attack on Video Classification +2
no code implementations • 25 Oct 2021 • Rui Xu, Xiangyu Xu, Kai Chen, Bolei Zhou, Chen Change Loy
Transformer becomes prevalent in computer vision, especially for high-level vision tasks.
no code implementations • 17 Oct 2021 • Zhong-qi K. Tian, Kai Chen, Songting Li, David W. McLaughlin, Douglas Zhou
However, the interpretation of causal connectivity remains to be fully clarified, in particular, how causal connectivity depends on causality measures and how causal connectivity relates to structural connectivity.
no code implementations • 29 Sep 2021 • Kai Chen, Yongqiang Ma, Mingyang Sheng, Nanning Zheng
Inspired by the mechanism of human visual attention, in this paper, we propose a novel method of reconstructing visual stimulus images, which first decodes the distribution of visual attention from fMRI, and then reconstructs the visual images guided by visual attention.
1 code implementation • 8 Sep 2021 • Tao Gong, Kai Chen, Xinjiang Wang, Qi Chu, Feng Zhu, Dahua Lin, Nenghai Yu, Huamin Feng
In this work, considering the features of the same object instance are highly similar among frames in a video, a novel Temporal RoI Align operator is proposed to extract features from other frames feature maps for current frame proposals by utilizing feature similarity.
Ranked #1 on Video Instance Segmentation on YouTube-VIS
1 code implementation • ICCV 2021 • Kai Chen, Lanqing Hong, Hang Xu, Zhenguo Li, Dit-yan Yeung
By pre-training on SODA10M, a large-scale autonomous driving dataset, MultiSiam exceeds the ImageNet pre-trained MoCo-v2, demonstrating the potential of domain-specific pre-training.
no code implementations • 23 Aug 2021 • Jiangmiao Pang, Kai Chen, Qi Li, Zhihai Xu, Huajun Feng, Jianping Shi, Wanli Ouyang, Dahua Lin
In this work, we carefully revisit the standard training practice of detectors, and find that the detection performance is often limited by the imbalance during the training process, which generally consists in three levels - sample level, feature level, and objective level.
no code implementations • 19 Aug 2021 • Jiaze Wang, Kai Chen, Qi Dou
Furthermore, we design a recurrent reconstruction network for iterative residual refinement to progressively improve the reconstruction and correspondence estimations from coarse to fine.
no code implementations • 18 Aug 2021 • Liu Yang, Junxue Zhang, Di Chai, Leye Wang, Kun Guo, Kai Chen, Qiang Yang
In this paper, we proposed federated masked matrix factorization (FedMMF) to protect the data privacy in federated recommender systems without sacrificing efficiency and effectiveness.
no code implementations • 16 Aug 2021 • Cengguang Zhang, Junxue Zhang, Di Chai, Kai Chen
In this paper, we present Aegis, a trusted, automatic, and accurate verification framework to verify the security of VFL jobs.
1 code implementation • 14 Aug 2021 • Zhanghui Kuang, Hongbin Sun, Zhizhong Li, Xiaoyu Yue, Tsui Hin Lin, Jianyong Chen, Huaqiang Wei, Yiqin Zhu, Tong Gao, Wenwei Zhang, Kai Chen, Wayne Zhang, Dahua Lin
We present MMOCR-an open-source toolbox which provides a comprehensive pipeline for text detection and recognition, as well as their downstream tasks such as named entity recognition and key information extraction.
1 code implementation • 2 Aug 2021 • Shuang Li, Bingfeng Han, Zhenjie Yu, Chi Harold Liu, Kai Chen, Shuigen Wang
Human vision is often adversely affected by complex environmental factors, especially in night vision scenarios.
no code implementations • 29 Jul 2021 • Xiaodian Cheng, Wanhang Lu, Xinyang Huang, Shuihai Hu, Kai Chen
In recent years, federated learning (FL) has been widely applied for supporting decentralized collaborative learning scenarios.
1 code implementation • NeurIPS 2021 • Wenwei Zhang, Jiangmiao Pang, Kai Chen, Chen Change Loy
The framework, named K-Net, segments both instances and semantic categories consistently by a group of learnable kernels, where each kernel is responsible for generating a mask for either a potential instance or a stuff class.
Ranked #7 on Panoptic Segmentation on COCO test-dev
no code implementations • 21 Jun 2021 • Jianhua Han, Xiwen Liang, Hang Xu, Kai Chen, Lanqing Hong, Jiageng Mao, Chaoqiang Ye, Wei zhang, Zhenguo Li, Xiaodan Liang, Chunjing Xu
Experiments show that SODA10M can serve as a promising pre-training dataset for different self-supervised learning methods, which gives superior performance when fine-tuning with different downstream tasks (i. e., detection, semantic/instance segmentation) in autonomous driving domain.
no code implementations • CVPR 2021 • Haoang Li, Kai Chen, Ji Zhao, Jiangliu Wang, Pyojin Kim, Zhe Liu, Yun-hui Liu
In contrast, we propose the first approach suitable for both structured and unstructured scenes.
no code implementations • 21 May 2021 • Shijie Fang, Yuhang Cao, Xinjiang Wang, Kai Chen, Dahua Lin, Wayne Zhang
The performance of object detection, to a great extent, depends on the availability of large annotated datasets.
no code implementations • 13 May 2021 • Yingzhe He, Guozhu Meng, Kai Chen, Jinwen He, Xingbo Hu
Compared to the method of retraining from scratch, our approach can achieve 99. 0%, 95. 0%, 91. 9%, 96. 7%, 74. 1% accuracy rates and 66. 7$\times$, 75. 0$\times$, 33. 3$\times$, 29. 4$\times$, 13. 7$\times$ speedups on the MNIST, SVHN, CIFAR-10, Purchase, and ImageNet datasets, respectively.
4 code implementations • CVPR 2022 • Haodong Duan, Yue Zhao, Kai Chen, Dahua Lin, Bo Dai
In this work, we propose PoseC3D, a new approach to skeleton-based action recognition, which relies on a 3D heatmap stack instead of a graph sequence as the base representation of human skeletons.
Ranked #1 on Action Recognition on NTU RGB+D 120
no code implementations • 25 Mar 2021 • Peizhuo Lv, Pan Li, Shengzhi Zhang, Kai Chen, Ruigang Liang, Yue Zhao, Yingjiu Li
Most existing solutions embed backdoors in DNN model training such that DNN ownership can be verified by triggering distinguishable model behaviors with a set of secret inputs.
1 code implementation • 19 Mar 2021 • Yuxuan Chen, Jiangshan Zhang, Xuejing Yuan, Shengzhi Zhang, Kai Chen, XiaoFeng Wang, Shanqing Guo
In this paper, we present our systematization of knowledge for ASR security and provide a comprehensive taxonomy for existing work based on a modularized workflow.
no code implementations • 18 Mar 2021 • Kai Chen, Qinglei Kong, Yijue Dai, Yue Xu, Feng Yin, Lexi Xu, Shuguang Cui
Empowered by big data and machine learning, next-generation data-driven communication systems will be intelligent with the characteristics of expressiveness, scalability, interpretability, and especially uncertainty modeling, which can confidently involve diversified latent demands and personalized services in the foreseeable future.
1 code implementation • 18 Mar 2021 • Zheng Huang, Kai Chen, Jianhua He, Xiang Bai, Dimosthenis Karatzas, Shjian Lu, C. V. Jawahar
In this competition, we set up three tasks, namely, Scanned Receipt Text Localisation (Task 1), Scanned Receipt OCR (Task 2) and Key Information Extraction from Scanned Receipts (Task 3).
Key Information Extraction Optical Character Recognition (OCR) +1
1 code implementation • 10 Feb 2021 • Kai Chen, Guang Chen, Dan Xu, Lijun Zhang, Yuyao Huang, Alois Knoll
Although Transformer has made breakthrough success in widespread domains especially in Natural Language Processing (NLP), applying it to time series forecasting is still a great challenge.
1 code implementation • 8 Feb 2021 • Kai Chen, Qi Lv, Taihe Yi
In addition, an identification preserving loss is proposed to improve the discriminative of the MLS metric, and a multi-layer feature fusion module is proposed to improve the neural network's uncertainty estimation ability.
no code implementations • ICCV 2021 • Haoang Li, Kai Chen, Pyojin Kim, Kuk-Jin Yoon, Zhe Liu, Kyungdon Joo, Yun-hui Liu
Based on this map, we can detect all the VPs.
no code implementations • ICCV 2021 • Kai Chen, Qi Dou
The prior adaptation intrinsically associates the adopted prior with different objects, from which we can accurately reconstruct the 3D canonical model of the specific object for pose estimation.
no code implementations • 24 Dec 2020 • Yangyang Qu, Kai Chen, Chao Liu, Yongsheng Ou
To address this problem, we propose a real-time unsupervised generative adversarial network (GAN) containing multiple discriminators, i. e. a multi-scale discriminator, a texture discriminator, and a color discriminator.
no code implementations • 22 Dec 2020 • Kai Chen, Meng Niu, Qingcai Chen
In this work, we propose a Hierarchical Reasoning Graph Neural Network (HRGNN) for the automatic assessment of question-answer pairs.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +4
no code implementations • CVPR 2021 • Rui Xu, Xintao Wang, Kai Chen, Bolei Zhou, Chen Change Loy
In this work, taking SinGAN and StyleGAN2 as examples, we show that such capability, to a large extent, is brought by the implicit positional encoding when using zero padding in the generators.
no code implementations • 7 Dec 2020 • Jiaqi Wang, Kai Chen, Rui Xu, Ziwei Liu, Chen Change Loy, Dahua Lin
Feature reassembly, i. e. feature downsampling and upsampling, is a key operation in a number of modern convolutional network architectures, e. g., residual networks and feature pyramids.
no code implementations • 25 Nov 2020 • Linhao Luo, Liqi Yang, Ju Xin, Yixiang Fang, Xiaofeng Zhang, Xiaofei Yang, Kai Chen, Zhiyuan Zhang, Kai Liu
In particular, we technically propose a novel random CNN component that can randomly convolute non-adjacent features to capture their interaction information and learn feature embeddings of key attributes to make the final recommendation.
no code implementations • 21 Nov 2020 • Zilong Cheng, Yulin Li, Kai Chen, Jun Ma, Tong Heng Lee
Iterative linear quadratic regulator (iLQR) has gained wide popularity in addressing trajectory optimization problems with nonlinear system models.
no code implementations • 19 Nov 2020 • Di Chai, Leye Wang, Liu Yang, Junxue Zhang, Kai Chen, Qiang Yang
In this paper, we propose a holistic evaluation framework for FL called FedEval, and present a benchmarking study on seven state-of-the-art FL algorithms.
no code implementations • 8 Nov 2020 • Kai Chen, Twan van Laarhoven, Elena Marchiori
The heavy tail and skewness characteristics of such distributions in the spectral domain allow to capture long-range covariance of the signal in the time domain.
no code implementations • 5 Oct 2020 • Andrea Amorese, Andrea Marino, Martin Sundermann, Kai Chen, Zhiwei Hu, Thomas Willers, Fadi Choukani, Philippe Ohresser, Javier Herrero-Martin, Stefano Agrestini, Chien-Te Chen, Hong-Ji Lin, Maurits W. Haverkort, Silvia Seiro, Christoph Geibel, Frank Steglich, Liu Hao Tjeng, Gertrud Zwicknagl, Andrea Severing
The crystal-field ground state wave function of CeCu$_2$Si$_2$ has been investigated with linear polarized $M$-edge x-ray absorption spectroscopy from 250mK to 250K, thus covering the superconducting ($T_{\text{c}}$=0. 6K), the Kondo ($T_{\text{K}}$$\approx$20K) as well as the Curie-Weiss regime.
Strongly Correlated Electrons
1 code implementation • 20 Sep 2020 • Leye Wang, Di Chai, Xuanzhe Liu, Liyue Chen, Kai Chen
The Spatio-Temporal Traffic Prediction (STTP) problem is a classical problem with plenty of prior research efforts that benefit from traditional statistical learning and recent deep learning approaches.
2 code implementations • CVPR 2021 • Jiaqi Wang, Wenwei Zhang, Yuhang Zang, Yuhang Cao, Jiangmiao Pang, Tao Gong, Kai Chen, Ziwei Liu, Chen Change Loy, Dahua Lin
Instances of head classes dominate a long-tailed dataset and they serve as negative samples of tail categories.
no code implementations • 16 Aug 2020 • Hao Wang, Jingrong Chen, Xinchen Wan, Han Tian, Jiacheng Xia, Gaoxiong Zeng, Weiyan Wang, Kai Chen, Wei Bai, Junchen Jiang
Communication overhead poses an important obstacle to distributed DNN training and draws increasing attention in recent years.
no code implementations • 21 Jul 2020 • Zhaoxiong Yang, Shuihai Hu, Kai Chen
Our framework implements the representative Paillier homomorphic cryptosystem with high level synthesis for flexibility and portability, with careful optimization on the modular multiplication operation in terms of processing clock cycle, resource usage and clock frequency.
no code implementations • 7 Jul 2020 • Weiyan Wang, Cengguang Zhang, Liu Yang, Kai Chen, Kun Tan
However, due to the global synchronization nature, its performance can be significantly influenced by network bottlenecks caused by either static topology heterogeneity or dynamic bandwidth contentions.
1 code implementation • 16 May 2020 • Zhaoyi Gu, Lele Liao, Kai Chen, Jing Lu
Extracting the desired speech from a mixture is a meaningful and challenging task.
1 code implementation • 15 May 2020 • Hongsheng Chen, Teng Xiang, Kai Chen, Jing Lu
Acoustic echo cannot be entirely removed by linear adaptive filters due to the nonlinear relationship between the echo and far-end signal.
no code implementations • 16 Apr 2020 • Kai Chen, Fayuan Li, Baotian Hu, Weihua Peng, Qingcai Chen, Hong Yu
We further design a reconstruction mechanism with a novel objective function that can reconstruct the whole entry of the used data sequentially from the hidden states of the decoder, which aids the accuracy of the generated text.
1 code implementation • 7 Apr 2020 • Kai Chen, Yuhang Cao, Chen Change Loy, Dahua Lin, Christoph Feichtenhofer
Feature pyramid networks have been widely adopted in the object detection literature to improve feature representations for better handling of variations in scale.
no code implementations • 6 Apr 2020 • Kai Chen, Jian Yao, Jingmin Tu, Yahui Liu, Yinxuan Li, Li Li
Recently, works on improving the naturalness of stitching images gain more and more extensive attention.
no code implementations • 30 Dec 2019 • Qinghe Jing, Weiyan Wang, Junxue Zhang, Han Tian, Kai Chen
The scarcity of data and isolated data islands encourage different organizations to share data with each other to train machine learning models.
no code implementations • 23 Dec 2019 • Yi-Zheng Zhen, Yingqiu Mao, Kai Chen, Francesco Buscemi, Oscar Dahlsten
The ability of quantum devices to preserve or distribute entanglement is essential in employing quantum technologies.
Quantum Physics
3 code implementations • ECCV 2020 • Jiaqi Wang, Wenwei Zhang, Yuhang Cao, Kai Chen, Jiangmiao Pang, Tao Gong, Jianping Shi, Chen Change Loy, Dahua Lin
To tackle the difficulty of precise localization in the presence of displacements with large variance, we further propose a two-step localization scheme, which first predicts a range of movement through bucket prediction and then pinpoints the precise position within the predicted bucket.
no code implementations • 28 Nov 2019 • Yingzhe He, Guozhu Meng, Kai Chen, Xingbo Hu, Jinwen He
In order to unveil the security weaknesses and aid in the development of a robust deep learning system, we undertake an investigation on attacks towards deep learning, and analyze these attacks to conclude some findings in multiple views.
no code implementations • 21 Nov 2019 • Jiaxu Chen, Jing Hao, Kai Chen, Di Xie, Shicai Yang, ShiLiang Pu
This paper introduces an end-to-end audio classification system based on raw waveforms and mix-training strategy.
1 code implementation • 21 Nov 2019 • Yongchao Xu, Mingtao Fu, Qimeng Wang, Yukang Wang, Kai Chen, Gui-Song Xia, Xiang Bai
Yet, the widely adopted horizontal bounding box representation is not appropriate for ubiquitous oriented objects such as objects in aerial images and scene texts.
Ranked #42 on Object Detection In Aerial Images on DOTA (using extra training data)
15 code implementations • 20 Nov 2019 • Minghui Liao, Zhaoyi Wan, Cong Yao, Kai Chen, Xiang Bai
Recently, segmentation-based methods are quite popular in scene text detection, as the segmentation results can more accurately describe scene text of various shapes such as curve text.
Ranked #6 on Scene Text Detection on MSRA-TD500
no code implementations • 14 Aug 2019 • Kai Chen, Zhongrui Lin, Jian Wan, Chungen Xu
In cloud security, traditional searchable encryption (SE) requires high computation and communication overhead for dynamic search and update.
no code implementations • 7 Aug 2019 • Kai Chen, Zhongrui Lin, Jian Wan, Lei Xu, Chungen Xu
To address this, this paper proposes secure and efficient multi-keyword ranked search over encrypted cloud data for multi-owner model based on searching adversarial networks.
144 code implementations • 17 Jun 2019 • Kai Chen, Jiaqi Wang, Jiangmiao Pang, Yuhang Cao, Yu Xiong, Xiaoxiao Li, Shuyang Sun, Wansen Feng, Ziwei Liu, Jiarui Xu, Zheng Zhang, Dazhi Cheng, Chenchen Zhu, Tianheng Cheng, Qijie Zhao, Buyu Li, Xin Lu, Rui Zhu, Yue Wu, Jifeng Dai, Jingdong Wang, Jianping Shi, Wanli Ouyang, Chen Change Loy, Dahua Lin
In this paper, we introduce the various features of this toolbox.
no code implementations • 12 Jun 2019 • Di Chai, Leye Wang, Kai Chen, Qiang Yang
The key principle of federated learning is training a machine learning model without needing to know each user's personal raw private data.
no code implementations • ACL 2019 • Nan Du, Kai Chen, Anjuli Kannan, Linh Tran, Yu-Hui Chen, Izhak Shafran
This paper describes novel models tailored for a new application, that of extracting the symptoms mentioned in clinical conversations along with their status.